OneSearch-V2: 一种增强潜在推理的自蒸馏生成搜索框架
OneSearch-V2: The Latent Reasoning Enhanced Self-distillation Generative Search Framework
AI总结:
OneSearch-V2通过引入潜在推理增强模块、自蒸馏训练流程和行为偏好对齐优化系统,提升复杂查询理解、用户意图挖掘和业务效果,实现搜索性能和用户体验的显著提升。
摘要:
生成检索(GR)已成为现代搜索系统有前景的范式。与多阶段级联架构相比,它提供了端到端联合优化和高计算效率的优势。OneSearch作为代表性工业级部署的生成搜索框架,带来了显著的商业和运营效益。然而,其对复杂查询的理解不足、对潜在用户意图的利用效率低以及对狭窄历史偏好过拟合限制了进一步性能提升。为解决这些问题,我们提出OneSearch-V2,一种增强潜在推理的自蒸馏生成搜索框架。它包含三个关键创新:(1)一个增强思考的复杂查询理解模块,使深度查询理解成为可能,克服了直接推断的浅层语义匹配限制;(2)一个内化推理的自蒸馏训练流程,通过隐式上下文学习揭示用户潜在且精确的电商意图,超越日志拟合;(3)一个行为偏好对齐优化系统,通过直接用户反馈解决单个转化指标导致的奖励黑客问题。广泛的离线评估证明了OneSearch-V2强大的查询识别和用户画像能力。在线A/B测试进一步验证了其商业有效性,产生+3.98%的物品点击率、+2.07%的买家量和+2.11%的订单量增长。人工评估进一步确认了搜索体验质量的提升,页面好评率提高+1.37%,查询-物品相关性提高+1.65%。更重要的是,OneSearch-V2有效缓解了常见搜索系统问题,如信息泡沫和长尾稀疏性,而无需增加推理成本或服务延迟。
英文摘要:
Generative Retrieval (GR) has emerged as a promising paradigm for modern search systems. Compared to multi-stage cascaded architecture, it offers advantages such as end-to-end joint optimization and high computational efficiency. OneSearch, as a representative industrial-scale deployed generative search framework, has brought significant commercial and operational benefits. However, its inadequate understanding of complex queries, inefficient exploitation of latent user intents, and overfitting to narrow historical preferences have limited its further performance improvement. To address these challenges, we propose OneSearch-V2, a latent reasoning enhanced self-distillation generative search framework. It contains three key innovations: (1) a thought-augmented complex query understanding module, which enables deep query understanding and overcomes the shallow semantic matching limitations of direct inference; (2) a reasoning-internalized self-distillation training pipeline, which uncovers users' potential yet precise e-commerce intentions beyond log-fitting through implicit in-context learning; (3) a behavior preference alignment optimization system, which mitigates reward hacking arising from the single conversion metric, and addresses personal preference via direct user feedback. Extensive offline evaluations demonstrate OneSearch-V2's strong query recognition and user profiling capabilities. Online A/B tests further validate its business effectiveness, yielding +3.98\% item CTR, +2.07\% buyer volume, and +2.11\% order volume. Manual evaluation further confirms gains in search experience quality, with +1.37\% in page good rate and +1.65\% in query-item relevance. More importantly, OneSearch-V2 effectively mitigates common search system issues such as information bubbles and long-tail sparsity, without incurring additional inference costs or serving latency.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。